Pith. sign in

REVIEW 2 cited by

Diffusion Schr\"odinger Bridge Matching

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2303.16852 v3 pith:BIEUWDZG submitted 2023-03-29 stat.ML cs.LG

classification stat.MLcs.LG
keywords transportdiffusiondsbmmatchingmethodsodingerproblemsschr
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Solving transport problems, i.e. finding a map transporting one given distribution to another, has numerous applications in machine learning. Novel mass transport methods motivated by generative modeling have recently been proposed, e.g. Denoising Diffusion Models (DDMs) and Flow Matching Models (FMMs) implement such a transport through a Stochastic Differential Equation (SDE) or an Ordinary Differential Equation (ODE). However, while it is desirable in many applications to approximate the deterministic dynamic Optimal Transport (OT) map which admits attractive properties, DDMs and FMMs are not guaranteed to provide transports close to the OT map. In contrast, Schr\"odinger bridges (SBs) compute stochastic dynamic mappings which recover entropy-regularized versions of OT. Unfortunately, existing numerical methods approximating SBs either scale poorly with dimension or accumulate errors across iterations. In this work, we introduce Iterative Markovian Fitting (IMF), a new methodology for solving SB problems, and Diffusion Schr\"odinger Bridge Matching (DSBM), a novel numerical algorithm for computing IMF iterates. DSBM significantly improves over previous SB numerics and recovers as special/limiting cases various recent transport methods. We demonstrate the performance of DSBM on a variety of problems.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Sample complexity of Schr\"odinger potential estimation

    cs.LG 2025-06 conditional novelty 7.0 of 10

    An empirical KL minimizer over log-potentials estimates Schrödinger bridge potentials with terminal excess KL risk O(log^2 n / n) in the realizable case, even when the target distribution has unbounded support.

  2. Multi-marginal temporal Schr\"odinger Bridge Matching from unpaired data

    cs.LG 2025-10 reject novelty 5.0 of 10

    MMtSBM extends diffusion Schrödinger bridge matching to multiple time marginals via a factorized iterative Markovian fitting algorithm, claiming state-of-the-art trajectory inference and video generation from unpaired data.

Pith tools